| 2025-08-19 00:55:35 - INFO - Loading model: google/gemma-3-4b-it | |
| 2025-08-19 00:55:37 - INFO - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). | |
| 2025-08-19 00:55:50 - INFO - Model loaded in 14.81 seconds | |
| 2025-08-19 00:55:50 - INFO - GPU Memory Usage after model load: 8201.85 MB | |
| 2025-08-19 00:55:58 - INFO - [0cfe1e16-f6d4-4f20-9091-9719eee547e3] Received new video inference request. Prompt: 'Please describe the video.', Video: 'messi_part_001.mp4' | |
| 2025-08-19 00:55:58 - INFO - [0cfe1e16-f6d4-4f20-9091-9719eee547e3] Video saved to temporary file: temp_videos/0cfe1e16-f6d4-4f20-9091-9719eee547e3.mp4 | |
| 2025-08-19 00:55:58 - INFO - [0cfe1e16-f6d4-4f20-9091-9719eee547e3] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-19 00:56:04 - INFO - [0cfe1e16-f6d4-4f20-9091-9719eee547e3] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-19 00:56:04 - INFO - [0cfe1e16-f6d4-4f20-9091-9719eee547e3] 30 frames saved to temp_videos/0cfe1e16-f6d4-4f20-9091-9719eee547e3 | |
| 2025-08-19 00:56:05 - INFO - Prompt token length: 7961 | |